Timeline for Minimizing KL divergence: the asymmetry, when will the solution be the same?
Current License: CC BY-SA 3.0
4 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Apr 28, 2017 at 13:57 | comment | added | Dirk | Well, OP minimizes over a constraint set $E$, i.e. seeking the "closest distribution to $p$ that comes from $E$". Makes sense to me. | |
| Apr 28, 2017 at 12:36 | comment | added | Paul Siegel | I'm a little confused: isn't $D(q || p)$ minimized at $q = p$ since $p \log \frac{p}{p} = 0$? Isn't it more normal to maximize KL-divergence? | |
| Apr 28, 2017 at 11:47 | answer | added | Dirk | timeline score: 5 | |
| Apr 28, 2017 at 3:10 | history | asked | Sung-En Chiu | CC BY-SA 3.0 |